{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,23]],"date-time":"2026-07-23T15:38:18Z","timestamp":1784821098603,"version":"3.55.0"},"publisher-location":"Cham","reference-count":41,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031726576","type":"print"},{"value":"9783031726583","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,10,2]],"date-time":"2024-10-02T00:00:00Z","timestamp":1727827200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,10,2]],"date-time":"2024-10-02T00:00:00Z","timestamp":1727827200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025]]},"DOI":"10.1007\/978-3-031-72658-3_13","type":"book-chapter","created":{"date-parts":[[2024,10,2]],"date-time":"2024-10-02T03:32:37Z","timestamp":1727839957000},"page":"216-233","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":398,"title":["MMBench: Is Your Multi-modal Model an\u00a0All-Around Player?"],"prefix":"10.1007","author":[{"given":"Yuan","family":"Liu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haodong","family":"Duan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuanhan","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bo","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Songyang","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wangbo","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yike","family":"Yuan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiaqi","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Conghui","family":"He","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ziwei","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kai","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dahua","family":"Lin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,10,2]]},"reference":[{"key":"13_CR1","unstructured":"01-ai: Yi-vl (2023). https:\/\/huggingface.co\/01-ai\/Yi-VL-34B"},{"key":"13_CR2","doi-asserted-by":"crossref","unstructured":"Agrawal, H., et al.: Nocaps: novel object captioning at scale. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 8948\u20138957 (2019)","DOI":"10.1109\/ICCV.2019.00904"},{"key":"13_CR3","first-page":"23716","volume":"35","author":"JB Alayrac","year":"2022","unstructured":"Alayrac, J.B., Donahue, J., Luc, P., Miech, A., Barr, I., Hasson, Y., Lenc, K., Mensch, A., Millican, K., Reynolds, M., et al.: Flamingo: a visual language model for few-shot learning. Adv. Neural. Inf. Process. Syst. 35, 23716\u201323736 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"13_CR4","unstructured":"Bai, J., et al.: Qwen-vl: a frontier large vision-language model with versatile abilities. arXiv preprint arXiv:2308.12966 (2023)"},{"key":"13_CR5","first-page":"1877","volume":"33","author":"T Brown","year":"2020","unstructured":"Brown, T., et al.: Language models are few-shot learners. Adv. Neural. Inf. Process. Syst. 33, 1877\u20131901 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"13_CR6","doi-asserted-by":"crossref","unstructured":"Chen, L., et al.: Sharegpt4v: Improving large multi-modal models with better captions. arXiv preprint arXiv:2311.12793 (2023)","DOI":"10.1007\/978-3-031-72643-9_22"},{"key":"13_CR7","unstructured":"Chen, X., et al.: Microsoft coco captions: Data collection and evaluation server. arXiv preprint arXiv:1504.00325 (2015)"},{"key":"13_CR8","unstructured":"Contributors, X.: Xtuner: A toolkit for efficiently fine-tuning llm (2023). https:\/\/github.com\/InternLM\/xtuner"},{"key":"13_CR9","unstructured":"Dai, W., et al.: Instructblip: Towards general-purpose vision-language models with instruction tuning. arXiv preprint arXiv:2305.06500 (2023)"},{"key":"13_CR10","unstructured":"Dong, X., et al.: Internlm-xcomposer2: Mastering free-form text-image composition and comprehension in vision-language large model. arXiv preprint arXiv:2401.16420 (2024)"},{"key":"13_CR11","doi-asserted-by":"crossref","unstructured":"Du, Z., et al.: Glm: general language model pretraining with autoregressive blank infilling. In: Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 320\u2013335 (2022)","DOI":"10.18653\/v1\/2022.acl-long.26"},{"key":"13_CR12","doi-asserted-by":"crossref","unstructured":"Fodor, J.A.: The modularity of mind. MIT press (1983)","DOI":"10.7551\/mitpress\/4737.001.0001"},{"key":"13_CR13","unstructured":"Fu, C., et al.: Mme: A comprehensive evaluation benchmark for multimodal large language models. ArXiv abs\/2306.13394 (2023). https:\/\/api.semanticscholar.org\/CorpusID:259243928"},{"key":"13_CR14","unstructured":"Gong, T., et al.: Multimodal-gpt: a vision and language model for dialogue with humans (2023)"},{"key":"13_CR15","doi-asserted-by":"crossref","unstructured":"Goyal, Y., Khot, T., Summers-Stay, D., Batra, D., Parikh, D.: Making the v in vqa matter: Elevating the role of image understanding in visual question answering. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6904\u20136913 (2017)","DOI":"10.1109\/CVPR.2017.670"},{"key":"13_CR16","doi-asserted-by":"crossref","unstructured":"Gurari, D., et al.: Vizwiz grand challenge: Answering visual questions from blind people. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3608\u20133617 (2018)","DOI":"10.1109\/CVPR.2018.00380"},{"key":"13_CR17","unstructured":"Hu, E.J., et al.: Lora: Low-rank adaptation of large language models. arXiv preprint arXiv:2106.09685 (2021)"},{"key":"13_CR18","doi-asserted-by":"crossref","unstructured":"Hudson, D.A., Manning, C.D.: Gqa: a new dataset for real-world visual reasoning and compositional question answering. In: Proceedings of the IEEE\/CVF Conference on Computer Vision And Pattern Recognition, pp. 6700\u20136709 (2019)","DOI":"10.1109\/CVPR.2019.00686"},{"key":"13_CR19","unstructured":"Lauren\u00e7on, H., et al.: Obelics: An open web-scale filtered dataset of interleaved image-text documents (2023)"},{"key":"13_CR20","unstructured":"Li, J., Li, D., Savarese, S., Hoi, S.: Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models. arXiv preprint arXiv:2301.12597 (2023)"},{"key":"13_CR21","doi-asserted-by":"crossref","unstructured":"Liu, H., Li, C., Li, Y., Lee, Y.J.: Improved baselines with visual instruction tuning. arXiv preprint arXiv:2310.03744 (2023)","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"13_CR22","unstructured":"Liu, H., Li, C., Wu, Q., Lee, Y.J.: Visual instruction tuning. arXiv preprint arXiv:2304.08485 (2023)"},{"key":"13_CR23","first-page":"2507","volume":"35","author":"P Lu","year":"2022","unstructured":"Lu, P., et al.: Learn to explain: multimodal reasoning via thought chains for science question answering. Adv. Neural. Inf. Process. Syst. 35, 2507\u20132521 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"13_CR24","doi-asserted-by":"crossref","unstructured":"Marino, K., Rastegari, M., Farhadi, A., Mottaghi, R.: Ok-vqa: a visual question answering benchmark requiring external knowledge. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3195\u20133204 (2019)","DOI":"10.1109\/CVPR.2019.00331"},{"key":"13_CR25","doi-asserted-by":"crossref","unstructured":"Oaksford, M., Chater, N.: Bayesian rationality: The probabilistic approach to human reasoning. Oxford University Press (2007)","DOI":"10.1093\/acprof:oso\/9780198524496.001.0001"},{"key":"13_CR26","unstructured":"OpenAI: Gpt-4 technical report. ArXivabs\/arXiv: 2303.08774 (2023)"},{"key":"13_CR27","unstructured":"OpenBMB: Minicpm: Unveiling the potential of end-side large language models (2024)"},{"key":"13_CR28","first-page":"27730","volume":"35","author":"L Ouyang","year":"2022","unstructured":"Ouyang, L., et al.: Training language models to follow instructions with human feedback. Adv. Neural. Inf. Process. Syst. 35, 27730\u201327744 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"issue":"8","key":"13_CR29","first-page":"9","volume":"1","author":"A Radford","year":"2019","unstructured":"Radford, A., Wu, J., Child, R., Luan, D., Amodei, D., Sutskever, I., et al.: Language models are unsupervised multitask learners. OpenAI Blog 1(8), 9 (2019)","journal-title":"OpenAI Blog"},{"key":"13_CR30","doi-asserted-by":"crossref","unstructured":"Singh, A., et al.: Towards vqa models that can read. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8317\u20138326 (2019)","DOI":"10.1109\/CVPR.2019.00851"},{"key":"13_CR31","unstructured":"Team, G., et\u00a0al.: Gemini: a family of highly capable multimodal models. arXiv preprint arXiv:2312.11805 (2023)"},{"key":"13_CR32","unstructured":"Team, I.: Internlm: a multilingual language model with progressively enhanced capabilities (2023). https:\/\/github.com\/InternLM\/InternLM-techreport"},{"key":"13_CR33","unstructured":"Touvron, H., et\u00a0al.: Llama: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971 (2023)"},{"key":"13_CR34","unstructured":"Wang, W., et al.: Cogvlm: Visual expert for pretrained language models. ArXiv abs\/ arXiv: 2311.03079 (2023), https:\/\/api.semanticscholar.org\/CorpusID:265034288"},{"key":"13_CR35","doi-asserted-by":"crossref","unstructured":"Xu, P., et al.: Lvlm-ehub: a comprehensive evaluation benchmark for large vision-language models (2023)","DOI":"10.1109\/TPAMI.2024.3507000"},{"key":"13_CR36","unstructured":"Ye, Q., et\u00a0al.: mplug-owl: Modularization empowers large language models with multimodality. arXiv preprint arXiv:2304.14178 (2023)"},{"key":"13_CR37","unstructured":"Ye, Q., et al.: mplug-owl2: Revolutionizing multi-modal large language model with modality collaboration. ArXiv arXiv: 2311.04257 (2023). https:\/\/api.semanticscholar.org\/CorpusID:265050943"},{"key":"13_CR38","doi-asserted-by":"publisher","first-page":"67","DOI":"10.1162\/tacl_a_00166","volume":"2","author":"P Young","year":"2014","unstructured":"Young, P., Lai, A., Hodosh, M., Hockenmaier, J.: From image descriptions to visual denotations: new similarity metrics for semantic inference over event descriptions. Trans. Associat. Comput. Linguist. 2, 67\u201378 (2014)","journal-title":"Trans. Associat. Comput. Linguist."},{"key":"13_CR39","unstructured":"Zheng, L., et al.: Judging llm-as-a-judge with mt-bench and chatbot arena (2023)"},{"key":"13_CR40","doi-asserted-by":"crossref","unstructured":"Zhou, L., Xu, C., Corso, J.: Towards automatic learning of procedures from web instructional videos. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a032 (2018)","DOI":"10.1609\/aaai.v32i1.12342"},{"key":"13_CR41","unstructured":"Zhu, D., Chen, J., Shen, X., Li, X., Elhoseiny, M.: Minigpt-4: Enhancing vision-language understanding with advanced large language models. arXiv preprint arXiv:2304.10592 (2023)"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-72658-3_13","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,28]],"date-time":"2024-11-28T23:53:44Z","timestamp":1732838024000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72658-3_13"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,2]]},"ISBN":["9783031726576","9783031726583"],"references-count":41,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72658-3_13","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10,2]]},"assertion":[{"value":"2 October 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Milan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2024.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}